Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 838
    Prev
    Next
    INDEX
    Explanations

    phrases related to media coverage and news analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.14
    0.7%
    373
    +0.13
    0.6%
    382
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.14
    0.07
    382
    +0.13
    0.06
    764
    +0.12
    0.06
    Negative Logits
    audi
    -0.64
     bene
    -0.62
    amiya
    -0.60
     Neurolog
    -0.57
    overe
    -0.57
     absence
    -0.57
     Beng
    -0.57
     Liang
    -0.55
     reserve
    -0.54
    fer
    -0.53
    POSITIVE LOGITS
     traction
    0.88
    chy
    0.80
    retty
    0.79
     foothold
    0.77
    started
    0.75
     grips
    0.72
     sidx
    0.71
     acquainted
    0.70
     bearings
    0.69
     mileage
    0.68
    Activations Density 1.048%

    No Known Activations